CN110363350A - A kind of regional air pollutant analysis method based on complex network - Google Patents
A kind of regional air pollutant analysis method based on complex network Download PDFInfo
- Publication number
- CN110363350A CN110363350A CN201910633683.7A CN201910633683A CN110363350A CN 110363350 A CN110363350 A CN 110363350A CN 201910633683 A CN201910633683 A CN 201910633683A CN 110363350 A CN110363350 A CN 110363350A
- Authority
- CN
- China
- Prior art keywords
- node
- value
- air
- website
- complex network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The regional air pollutant analysis method based on complex network that the invention discloses a kind of, comprising the following steps: S1. establishes air complex network model according to the air quality data in the area of data with existing；S2. the air pollutants complex network model based on foundation carries out region division using air pollutants complex network model of the CNM algorithm to foundation；S3. unknown node air quality data is predicted.The present invention establishes a kind of atmosphere pollution communication network model, and dispersion of pollutants path and key node are excavated on this basis, each monitoring station is abstracted on the node of complex network, by dispersion of pollutants path be abstracted into complex network while and while weight on, and Air Quality later will be predicted by this network.Can more efficiently analyze the communication network of air pollutants by the method, and it is predictable go out after air quality data, can for Air Quality Analysis, predict provide valuable reference.
Description
Technical field
The present invention relates to air contamination analysis, more particularly to a kind of regional air pollutant analysis based on complex network
Method.
Background technique
With the continuous development of China's economy, the air quality problems of China's most area are also got worse.It is serious
Air pollution causes serious influence to the body of people and life；The air pollution of different zones is monitored, it is right
There is very important meaning in air pollution treatment.
Atmosphere pollution communication network is influenced by many factors, most important three factors are as follows: orographic factor, meteorology
Factor and pollutant factor.Orographic factor specifically includes that the horizontal distance between two areas, if there are mountain range, height above sea level
Difference etc..Meteorologic factor has: wind speed, wind direction, temperature, humidity, rainfall, sand and dust etc..
The quality of air quality reflects air pollution degree, and the concentration level of pollutant judges through the air.
The pollutant of air pollution mainly has fine particle (PM2.5), pellet (PM10), sulfur dioxide (SO2), nitrogen dioxide
(NO2), ozone (O3), nitric oxide (CO) etc..Air quality index AQI (Air Quality Index) calculation method is as follows:
(1) IAQI of each pollutant is calculatedP:
In formula:
IAQIPRefer to the air quality separate index number of pollutant project p；
CPRefer to the mass concentration value of pollutant project P；
BPHiRefer in " surrounding air index technique provide (tentative) " with CPThe high-value of similar pollutant concentration limit value；
BPLoRefer in " surrounding air index technique provide (tentative) " with CPThe low-value of similar pollutant concentration limit value；
IAQIHiRefer in " surrounding air index technique provide (tentative) " with BPHiCorresponding air quality separate index number；
IAQILoRefer in " surrounding air index technique provide (tentative) " with BPLoCorresponding air quality separate index number.
(2) AQI is calculated
AQI=max (IAQI1,IAQI2,IAQI3..., IAQIn}
In formula: IAQI refers to air quality separate index number；N refers to pollutant project.
But tool is presently, since China is geographical vast, establishing the air quality monitoring station covered all around is very
Difficult, this causes us that can not understand current Air Quality in all directions in time, can not for Air Quality Analysis,
Prediction provides valuable reference, and establishes air monitering website and need to expend a large amount of manpower and material resources, by excavating crucial section
Point can also provide strong reference for the foundation of air quality monitoring station's point.
Summary of the invention
The regional air quality based on complex network that it is an object of the invention to overcome the deficiencies of the prior art and provide a kind of
Pollutant analysis method, can more efficiently analyze the communication network of air pollutants, and it is predictable go out after air matter
Measure data.
The purpose of the present invention is achieved through the following technical solutions: a kind of regional air pollution based on complex network
Object analysis method, comprising the following steps:
S1. according to the air quality data in the area of data with existing, air complex network model is established:
S101. the node in survey region is abstracted:
Air model based on complex network is mainly the network for establishing the space correlation in air between each component variable
Model, thus establish abstract node be based on the air quality all data of a certain monitoring point, air quality it is each
The time series of item data is the monitoring point from each city, according to the air quality data to be studied, by a certain monitoring
The monitoring data of point are to be abstracted as node, specifically:
Assuming that being directed to this air quality variable of AQI, N number of monitoring point, corresponding sequence are set up altogether in institute's survey region
X is used respectively1, X2, X3..., XN, then each sequence is abstracted as a node, the set of node is indicated with V, then:
V={ X1, X2, X3..., XN}
In formula: Xi=(x1, x2, x3..., xT)；I=1,2,3 ..., N, wherein T represents the length of access time sequence；
S102. the side between node is abstracted:
The diffusion path of pollutant often more than one needs the path for selecting to be easiest to propagate, by the difficulty of this propagation
Easy degree is known as spread restraint value Value, and the smallest path definition of spread restraint value Value is crucial propagation path, website
Between there are the condition on side, it is specific as follows:
Wherein, DijIndicate website i, the distance between j；ΔFij(t) indicate that the wind factor between t moment website i, j is poor
Value；P indicates website i, the pollutant related coefficient between j；ValueijIndicate website i, dispersion of pollutants inhibiting value between j；When
Lij(t) be 0 when indicate website between be not present dispersion of pollutants path, for 1 indicate there are paths；
Using adjacency matrix A come the company of expression side, in adjacency matrix A:
Wherein, aijThe i-th row jth column of adjacency matrix A are represented, being worth to represent for 1 has certain correlation between node i, j；
S103. between calculate node side weight:
According to the diffusion correlation theory of gas, the weights omega propagated between t moment website i and website jij(t) as follows:
In formula, Δ HijIndicate that height above sea level is poor between website；ΔSijIndicate the horizontal distance between website；ΔAQIij(t) in t
Moment indicates the difference of AQI between website；Rij(t) wind factor between t moment website is indicated；γ is correction coefficient, value
[0,1]；ε (t) indicates ultimate load ωij(t) undulating value；
Wherein wind factor Rij(t) it calculates as follows:
In formula:It is wind-force size, unit m/s；θij(t) be wind-force at website actual direction and website i angle, when
When it is greater than 90 degree, pollutant is not propagated；
It S104. is a complex network model G for thering is side to have the right by air pollutants network abstraction, fundamental includes
Node set P, line set L, side right set W, it may be assumed that
G=(P, L, W).
S2. the air pollutants complex network model based on foundation is complicated using air pollutants of the CNM algorithm to foundation
Network model carries out region division:
S201. CNM algorithm is used, initialization network is N number of corporations, i.e., each node is an independent corporations, at this point,
The module angle value Q=0 of initialization；Initial eijAnd aiMeet following condition:
ai=ki/2m
Wherein, eijFor the ratio of node i and all sides of j Lian Bianzhan network, aiThe degree of whole network is accounted for for the degree of node i
Ratio；kiFor the degree of node i, m is the item number on side total in network；In this way, the element of initial modularity Increment Matrix meets:
After obtaining introductory die lumpiness Increment Matrix, the most raft H that is made of the greatest member of its every a line；
S202. maximum Δ Q is selected from most raft Hij, merge corresponding corporations i and j, the corporations after label merging are
J, and update module degree Increment Matrix Δ Qij, most raft H and auxiliary vector ai:
a、ΔQiiUpdate: delete the i-th row and i column element, update jth row and jth column element, to obtain:
B, the most update of raft H: Δ Q is updated every timeijAfterwards, in Yao Gengxin most raft corresponding row and column greatest member；
C, auxiliary vector aiUpdate:
a′j=ai+aj；a′i=0
Meanwhile it recording and merging later module angle value Q+ Δ Qij；
S203. step S202 is repeated until all nodes in network are all grouped into a corporations.
S3. unknown node air quality data is predicted.
S301. the sub- corporations excavated using PageRank algorithm in optimal corporations (community structure that step S2 is obtained) are total
Property node:
After air pollutants complex network community structure is done optimal dividing, PageRank algorithm is recycled to excavate son
The contribution degree of node in corporations, and therefrom choose the general character node of sub- corporations；
PageRank value is determined by 3 factors: the first, connecting the number of nodes into present node；The second, present node sheet
Whether the significance level of body, this node itself are just a high quality node；Third, the quantity of present node connected out；By
The network of building is Undirected networks, will be connected into connect and regards same index as, node PageRank value calculation formula is as follows:
Wherein, PageRank (X) indicates the PageRank value of nodes X；PageRank(Yi) indicate each connection ingress X
Node YiPageRank value；Cout(Yi) indicate node YiThe quantity on all sides；B indicates all sections for being connected to nodes X
Point set；α is damped coefficient, value 0.85；N indicates total node number；
After being ranked up by different degree of the PageRank algorithm to sub- corporations' interior joint, choose ranking the first two node make
The general character node in region thus；
S302. the property node of node to be predicted is chosen:
The general character node of all sub- corporations is being excavated, and after having chosen node to be predicted, selected apart from section to be predicted
Property node of the two nearest general character nodes of point as prediction；
S303. the value of the AQI of unknown node is predicted:
The value of utilization level node air quality AQI goes the value of the AQI of prediction unknown node, and fundamental formular is as follows:
Wherein, ZiThe AQI value of representing characteristic node；ZoRepresent the AQI value of unknown node；ωiSection property node is represented pre-
Shared weight in survey；It is corresponding that the distribution principle of weight is that the inverse with node at a distance from unknown node accounts for all property nodes
The ratio of the sum of item is allocated, it may be assumed that
In formula: diRepresent the unknown node of node to be predicted and the distance of property node i.
Preferably, in the step S2, it is contemplated that some isolated node in the complex network model of foundation, because
Inherently there are the corporations of a part of individual node in this corporation divided, therefore carry out region division using CNM algorithm, in step
Following termination condition is set in the implementation procedure of rapid S203: in modularity Increment Matrix maximum element by just changing to negative when just stop
Only merge；Community structure at this time is best network community structure, and modularity O has maximum value at this time.
The beneficial effects of the present invention are: the present invention establishes a kind of atmosphere pollution communication network model, and basic herein
On excavate dispersion of pollutants path and key node, each monitoring station is abstracted on the node of complex network, will be polluted
Object propagation path be abstracted into complex network while and while weight on, and will by this network to Air Quality later
It is predicted.Can more efficiently analyze the communication network of air pollutants by the method, and it is predictable go out after sky
Gas qualitative data can provide valuable reference for Air Quality Analysis, prediction.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawing, but protection scope of the present invention is not limited to
It is as described below.
The present invention using complex network community excavation air section is divided, based on region division find with to
The similar node for predicting node, so that the air quality AQI situation to Cross Some Region Without Data predicts that concrete scheme is as follows:
As shown in Figure 1, a kind of regional air pollutant analysis method based on complex network, comprising the following steps:
S1. according to the air quality data in the area of data with existing, air complex network model is established:
S101. the node in survey region is abstracted:
Air model based on complex network is mainly the network for establishing the space correlation in air between each component variable
Model, thus establish abstract node be based on the air quality all data of a certain monitoring point, air quality it is each
The time series of item data is the monitoring point from each city, according to the air quality data to be studied, by a certain monitoring
The monitoring data of point are to be abstracted as node, specifically:
Assuming that being directed to this air quality variable of AQI, N number of monitoring point, corresponding sequence are set up altogether in institute's survey region
X is used respectively1, X2, X3..., XN, then each sequence is abstracted as a node, the set of node is indicated with V, then:
V={ X1, X2, X3..., XN}
In formula: Xi=(x1, x2, x3..., xT)；I=1,2,3 ..., N, wherein T represents the length of access time sequence；
S102. the side between node is abstracted:
The diffusion path of pollutant often more than one needs the path for selecting to be easiest to propagate, by the difficulty of this propagation
Easy degree is known as spread restraint value Value, and the smallest path definition of spread restraint value Value is crucial propagation path, website
Between there are the condition on side, it is specific as follows:
Wherein, DijIndicate website i, the distance between j；ΔFij(t) indicate that the wind factor between t moment website i, j is poor
Value；ρ indicates website i, the pollutant related coefficient between j；ValueijIndicate website i, dispersion of pollutants inhibiting value between j；When
Lij(t) be 0 when indicate website between be not present dispersion of pollutants path, for 1 indicate there are paths；
Using adjacency matrix A come the company of expression side, in adjacency matrix A:
Wherein, aijThe i-th row jth column of adjacency matrix A are represented, being worth to represent for 1 has certain correlation between node i, j；
S103. between calculate node side weight:
According to the diffusion correlation theory of gas, the weights omega propagated between t moment website i and website jij(t) as follows:
In formula, Δ HijIndicate that height above sea level is poor between website；ΔSijIndicate the horizontal distance between website；ΔAQIij(t) in t
Moment indicates the difference of AQI between website；Rij(t) wind factor between t moment website is indicated；γ is correction coefficient, value
[0,1]；ε (t) indicates ultimate load ωij(t) undulating value；
Wherein wind factor Rij(t) it calculates as follows:
In formula:It is wind-force size, unit m/s；θij(t) be wind-force at website actual direction and website i angle, when
When it is greater than 90 degree, pollutant is not propagated；
It S104. is a complex network model G for thering is side to have the right by air pollutants network abstraction, fundamental includes
Node set P, line set L, side right set W, it may be assumed that
G=(P, L, W).
S2. the air pollutants complex network model based on foundation is complicated using air pollutants of the CNM algorithm to foundation
Network model carries out region division:
S201. CNM algorithm is used, initialization network is N number of corporations, i.e., each node is an independent corporations, at this point,
The module angle value Q:0 of initialization；Initial eijAnd aiMeet following condition:
ai=ki/2m
Wherein, eijFor the ratio of node i and all sides of j Lian Bianzhan network, aiThe degree of whole network is accounted for for the degree of node i
Ratio；kiFor the degree of node i, m is the item number on side total in network；In this way, the element of initial modularity Increment Matrix meets:
After obtaining introductory die lumpiness Increment Matrix, the most raft H that is made of the greatest member of its every a line；
S202. maximum Δ Q is selected from most raft Hij, merge corresponding corporations i and j, the corporations after label merging are
J, and update module degree Increment Matrix Δ Qij, most raft H and auxiliary vector ai:
a、ΔQijUpdate: delete the i-th row and i column element, update jth row and jth column element, to obtain:
B, the most update of raft H: Δ Q is updated every timeijAfterwards, in Yao Gengxin most raft corresponding row and column greatest member；
C, auxiliary vector aiUpdate:
a′j=ai+aj；a′i=0
Meanwhile it recording and merging later module angle value Q+ Δ Qij；
S203. step S202 is repeated until all nodes in network are all grouped into a corporations.
S3. unknown node air quality data is predicted.
S301. the sub- corporations excavated using PageRank algorithm in optimal corporations (community structure that step S2 is obtained) are total
Property node:
After air pollutants complex network community structure is done optimal dividing, PageRank algorithm is recycled to excavate son
The contribution degree of node in corporations, and therefrom choose the general character node of sub- corporations；
PageRank value is determined by 3 factors: the first, connecting the number of nodes into present node；The second, present node sheet
Whether the significance level of body, this node itself are just a high quality node；Third, the quantity of present node connected out；By
It is Undirected networks in the network of building, will be connected into connect and regards same index as, node PageRank value calculation formula is as follows:
Wherein, PageRank (X) indicates the PageRank value of nodes X；PageRank(Yi) indicate each connection ingress X
Node YiPageRank value；Cout(Yi) indicate node YiThe quantity on all sides；B indicates all sections for being connected to nodes X
Point set；α is damped coefficient, value 0.85；N indicates total node number；
After being ranked up by different degree of the PageRank algorithm to sub- corporations' interior joint, choose ranking the first two node make
The general character node in region thus；
S302. the property node of node to be predicted is chosen:
The general character node of all sub- corporations is being excavated, and after having chosen node to be predicted, selected apart from section to be predicted
Property node of the two nearest general character nodes of point as prediction；
S303. the value of the AQI of unknown node is predicted:
The value of utilization level node air quality AQI goes the value of the AQI of prediction unknown node, and fundamental formular is as follows:
Wherein, ZiThe AQI value of representing characteristic node；ZoRepresent the AQI value of unknown node；ωiSection property node is represented pre-
Shared weight in survey；It is corresponding that the distribution principle of weight is that the inverse with node at a distance from unknown node accounts for all property nodes
The ratio of the sum of item is allocated, it may be assumed that
In formula: diRepresent the unknown node of node to be predicted and the distance of property node i.
In the step S2, it is contemplated that some isolated node in the complex network model of foundation, therefore divide
Corporations in inherently there are the corporations of a part of individual node, therefore region division is carried out using CNM algorithm, in step S203
Implementation procedure in following termination condition is set: in modularity Increment Matrix maximum element by just changing to negative when just stop closing
And；Community structure at this time is best network community structure, and modularity Q has maximum value at this time.
To sum up, the present invention establishes a kind of atmosphere pollution communication network model, and excavates pollutant on this basis
Each monitoring station (region or city) is abstracted on the node of complex network, by pollutant by propagation path and key node
Propagation path be abstracted into complex network while and while weight on, and will by this network to Air Quality later into
Row prediction.Can more efficiently analyze the communication network of air pollutants by the method, and it is predictable go out after air
Qualitative data can provide valuable reference for Air Quality Analysis, prediction.
The above is a preferred embodiment of the present invention, it should be understood that the present invention is not limited to shape described herein
Formula should not be viewed as excluding other embodiments, and can be used for other combinations, modification and environment, and can be in this paper institute
It states in contemplated scope, modifications can be made through the above teachings or related fields of technology or knowledge.And what those skilled in the art were carried out
Modifications and changes do not depart from the spirit and scope of the present invention, then all should be within the scope of protection of the appended claims of the present invention.
Claims (5)
1. a kind of regional air pollutant analysis method based on complex network, it is characterised in that: the following steps are included:
S1. according to the air quality data in the area of data with existing, air complex network model is established；
S2. the air pollutants complex network model based on foundation, using CNM algorithm to the air pollutants complex network of foundation
Model carries out region division；
S3. unknown node air quality data is predicted.
2. a kind of regional air pollutant analysis method based on complex network according to claim 1, it is characterised in that:
The step S1 includes following sub-step:
S101. the node in survey region is abstracted:
Air model based on complex network is mainly the network model for establishing the space correlation in air between each component variable,
Therefore establishing abstract node is all data of air quality based on the air quality all data of a certain monitoring point
Time series be the monitoring point from each city, according to the air quality data to be studied, by the prison of a certain monitoring point
Measured data is to be abstracted as node, specifically:
Assuming that being directed to this air quality variable of AQI, N number of monitoring point, corresponding sequence difference are set up in institute's survey region altogether
Use X1, X2, X3... XN, then each sequence is abstracted as a node, the set of node is indicated with V, then:
V={ X1, X2, X3..., XN}
In formula: Xi=(x1, x2, x3..., xT)；I=1,2,3 ..., N, wherein T represents the length of access time sequence；
S102. the side between node is abstracted:
The diffusion path of pollutant often more than one needs the path for selecting to be easiest to propagate, by the difficulty or ease journey of this propagation
Degree is known as spread restraint value Value, and the smallest path definition of spread restraint value Value is crucial propagation path, between website
It is specific as follows there are the condition on side:
Wherein, DijIndicate website i, the distance between j；ΔFij(t) the wind factor difference between t moment website i, j is indicated；ρ
Indicate website i, the pollutant related coefficient between j；ValueiiIndicate website i, dispersion of pollutants inhibiting value between j；Work as Lij
(t) be 0 when indicate website between be not present dispersion of pollutants path, for 1 indicate there are paths；
Using adjacency matrix A come the company of expression side, in adjacency matrix A:
Wherein, ajThe i-th row jth column of adjacency matrix A are represented, being worth to represent for 1 has certain correlation between node i, j；
S103. between calculate node side weight:
According to the diffusion correlation theory of gas, the weights omega propagated between t moment website i and website jij(t) as follows:
In formula, Δ HijIndicate that height above sea level is poor between website；ΔSijIndicate the horizontal distance between website；ΔAQIij(t) in t moment
Indicate the difference of AQI between website；Rij(t) wind factor between t moment website is indicated；γ is correction coefficient, value [0,
1]；ε (t) indicates ultimate load ωij(t) undulating value；
Wherein wind factor Rij(t) it calculates as follows:
In formula:It is wind-force size, unit m/s；θij(t) be website actual direction and website i place wind-force angle, when it greatly
When 90 degree, pollutant is not propagated；
It S104. is a complex network model G for thering is side to have the right by air pollutants network abstraction, fundamental includes node
Set P, line set L, side right set W, it may be assumed that
G=(P, L, W).
3. a kind of regional air pollutant analysis method based on complex network according to claim 1, it is characterised in that:
The step S2 includes following sub-step:
S201. CNM algorithm is used, initialization network is N number of corporations, i.e., each node is an independent corporations, at this point, initially
The module angle value Q=0 of change；Initial eijAnd aiMeet following condition:
ai=ki/2m
Wherein, eijFor the ratio of node i and all sides of j Lian Bianzhan network, aiFor node i degree account for whole network degree ratio
Value；kiFor the degree of node i, m is the item number on side total in network；In this way, the element of initial modularity Increment Matrix meets:
After obtaining introductory die lumpiness Increment Matrix, the most raft H that is made of the greatest member of its every a line；
S202. maximum Δ Q is selected from most raft Hij, merging corresponding corporations i and j, the corporations after label merging are j, and
Update module degree Increment Matrix Δ Qij, most raft H and auxiliary vector ai:
a、ΔQijUpdate: delete the i-th row and i column element, update jth row and jth column element, to obtain:
B, the most update of raft H: Δ Q is updated every timeijAfterwards, in Yao Gengxin most raft corresponding row and column greatest member；
C, auxiliary vector aiUpdate:
a′j=ai+aj；a′i=0
Meanwhile it recording and merging later module angle value Q+ Δ Qij；
S203. step S202 is repeated until all nodes in network are all grouped into a corporations.
4. a kind of regional air pollutant analysis method based on complex network according to claim 3, it is characterised in that:
In the step S2, it is contemplated that some isolated node in the complex network model of foundation, therefore in the corporations divided
Inherently there are the corporations of a part of individual node, therefore carry out region division using CNM algorithm, in the execution of step S203
Following termination condition is set in journey: in modularity Increment Matrix maximum element by just changing to negative when just stop merging；At this time
Community structure is best network community structure, and modularity Q has maximum value at this time.
5. a kind of regional air pollutant analysis method based on complex network according to claim 1, it is characterised in that:
The step S3 includes following sub-step:
S301. PageRank algorithm is utilized, sub- corporations' general character node in the community structure obtained to step S2 excavates:
After air pollutants complex network community structure is done optimal dividing, PageRank algorithm is recycled to excavate sub- corporations
In node contribution degree, and therefrom choose the general character node of sub- corporations；
PageRank value is determined by 3 factors: the first, connecting the number of nodes into present node；The second, present node itself
Whether significance level, this node itself are just a high quality node；Third, the quantity of present node connected out；Due to structure
The network built is Undirected networks, will be connected into connect and regards same index as, node PageRank value calculation formula is as follows:
Wherein, PageRank (X) indicates the PageRank value of nodes X；PageRank(Yi) indicate each section for connecting ingress X
Point YiPageRank value；Cout(Yi) indicate node YiThe quantity on all sides；B indicates all node collection for being connected to nodes X
It closes；α is damped coefficient, value 0.85；N indicates total node number；
After being ranked up by different degree of the PageRank algorithm to sub- corporations' interior joint, ranking the first two node is chosen as this
The general character node in region；
S302. the property node of node to be predicted is chosen:
Excavating the general character node of all sub- corporations, and after having chosen node to be predicted, selection apart from node to be predicted most
Property node of the two close general character nodes as prediction；
S303. the value of the AQI of unknown node is predicted:
The value of utilization level node air quality AQI goes the value of the AQI of prediction unknown node, and fundamental formular is as follows:
Wherein, ZiThe AQI value of representing characteristic node；ZoRepresent the AQI value of unknown node；ωiSection property node is represented in prediction
Shared weight；The distribution principle of weight be the inverse with node at a distance from unknown node account for all property node respective items it
The ratio of sum is allocated, it may be assumed that
In formula: diRepresent the unknown node of node to be predicted and the distance of property node i.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910633683.7A CN110363350B (en) | 2019-07-15 | 2019-07-15 | Regional air pollutant analysis method based on complex network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910633683.7A CN110363350B (en) | 2019-07-15 | 2019-07-15 | Regional air pollutant analysis method based on complex network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110363350A true CN110363350A (en) | 2019-10-22 |
| CN110363350B CN110363350B (en) | 2023-10-10 |
Family
ID=68219166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910633683.7A Active CN110363350B (en) | 2019-07-15 | 2019-07-15 | Regional air pollutant analysis method based on complex network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363350B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111538957A (en) * | 2020-04-21 | 2020-08-14 | 中科三清科技有限公司 | Method, device, equipment and medium for acquiring contribution degree of atmospheric pollutant source |
| CN111666646A (en) * | 2020-05-25 | 2020-09-15 | 上海市环境监测中心(上海长三角区域空气质量预测预报中心) | Method and system for identifying atmospheric pollution transmission key node based on complex network |
| CN111932874A (en) * | 2020-07-27 | 2020-11-13 | 中国科学技术大学 | Method and system for predicting air pollution trend by using motor vehicle GPS track |
| CN112541302A (en) * | 2020-12-23 | 2021-03-23 | 北京百度网讯科技有限公司 | Air quality prediction model training method, air quality prediction method and device |
| CN113344759A (en) * | 2021-06-30 | 2021-09-03 | 北京建筑大学 | Analysis method for mobile source pollution emission |
| CN114997506A (en) * | 2022-06-17 | 2022-09-02 | 西北师范大学 | Atmospheric pollution propagation path prediction method based on link prediction |
| CN116739189A (en) * | 2023-08-14 | 2023-09-12 | 中科三清科技有限公司 | Transmission tracing method and device, storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170185910A1 (en) * | 2015-12-28 | 2017-06-29 | International Business Machines Corporation | Steering graph mining algorithms applied to complex networks |
| CN107133398A (en) * | 2017-04-28 | 2017-09-05 | 河海大学 | A kind of river ethic Forecasting Methodology based on complex network |
| CN107194498A (en) * | 2017-04-28 | 2017-09-22 | 河海大学 | A kind of optimization method of hydrologic monitoring network |
| CN107608962A (en) * | 2017-09-12 | 2018-01-19 | 电子科技大学 | Pushing away based on complex network especially big selects data analysing method |
| WO2018214060A1 (en) * | 2017-05-24 | 2018-11-29 | 北京质享科技有限公司 | Small-scale air quality index prediction method and system for city |
| CN112598549A (en) * | 2020-12-23 | 2021-04-02 | 广东技术师范大学 | Learner potential overlapping community detection method, device, equipment and medium |
-
2019
- 2019-07-15 CN CN201910633683.7A patent/CN110363350B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170185910A1 (en) * | 2015-12-28 | 2017-06-29 | International Business Machines Corporation | Steering graph mining algorithms applied to complex networks |
| CN107133398A (en) * | 2017-04-28 | 2017-09-05 | 河海大学 | A kind of river ethic Forecasting Methodology based on complex network |
| CN107194498A (en) * | 2017-04-28 | 2017-09-22 | 河海大学 | A kind of optimization method of hydrologic monitoring network |
| WO2018214060A1 (en) * | 2017-05-24 | 2018-11-29 | 北京质享科技有限公司 | Small-scale air quality index prediction method and system for city |
| CN107608962A (en) * | 2017-09-12 | 2018-01-19 | 电子科技大学 | Pushing away based on complex network especially big selects data analysing method |
| CN112598549A (en) * | 2020-12-23 | 2021-04-02 | 广东技术师范大学 | Learner potential overlapping community detection method, device, equipment and medium |
Non-Patent Citations (3)
| Title |
|---|
| ROOPA SHREE.J ETAL.: "Low Power EMC Optimized Wireless Sensor Network for Air Pollution Monitoring System", 《INTERNATIONAL JOURNAL ON RECENT AND INNOVATION TRENDS IN COMPUTING AND COMMUNICATION》 * |
| 吴瑶: "区域大气污染物关键传播路径和重要节点挖掘方法研究", 《中国优秀硕士学位沦文全文数据库 基础科学辑》 * |
| 康西龙: "基于复杂网络的空气污染物传播关键路径和节点挖掘研究", 《中国优秀硕士学位沦文全文数据库 工程科技I辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111538957A (en) * | 2020-04-21 | 2020-08-14 | 中科三清科技有限公司 | Method, device, equipment and medium for acquiring contribution degree of atmospheric pollutant source |
| CN111538957B (en) * | 2020-04-21 | 2020-11-17 | 中科三清科技有限公司 | Method, device, equipment and medium for acquiring contribution degree of atmospheric pollutant source |
| CN111666646A (en) * | 2020-05-25 | 2020-09-15 | 上海市环境监测中心(上海长三角区域空气质量预测预报中心) | Method and system for identifying atmospheric pollution transmission key node based on complex network |
| CN111666646B (en) * | 2020-05-25 | 2023-03-28 | 上海市环境监测中心(上海长三角区域空气质量预测预报中心) | Method and system for identifying atmospheric pollution transmission key node based on complex network |
| CN111932874A (en) * | 2020-07-27 | 2020-11-13 | 中国科学技术大学 | Method and system for predicting air pollution trend by using motor vehicle GPS track |
| CN111932874B (en) * | 2020-07-27 | 2022-09-06 | 中国科学技术大学 | Method and system for predicting air pollution trend by using motor vehicle GPS track |
| CN112541302A (en) * | 2020-12-23 | 2021-03-23 | 北京百度网讯科技有限公司 | Air quality prediction model training method, air quality prediction method and device |
| CN112541302B (en) * | 2020-12-23 | 2024-02-06 | 北京百度网讯科技有限公司 | Air quality prediction model training method, air quality prediction method and device |
| CN113344759A (en) * | 2021-06-30 | 2021-09-03 | 北京建筑大学 | Analysis method for mobile source pollution emission |
| CN114997506A (en) * | 2022-06-17 | 2022-09-02 | 西北师范大学 | Atmospheric pollution propagation path prediction method based on link prediction |
| CN114997506B (en) * | 2022-06-17 | 2024-05-14 | 西北师范大学 | Atmospheric pollution propagation path prediction method based on link prediction |
| CN116739189A (en) * | 2023-08-14 | 2023-09-12 | 中科三清科技有限公司 | Transmission tracing method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110363350B (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363350A (en) | A kind of regional air pollutant analysis method based on complex network | |
| Liu et al. | CFD simulations of wind distribution in an urban community with a full-scale geometrical model | |
| CN103234883B (en) | A kind of method based on road traffic flow real-time estimation inner city PM2.5 concentration | |
| Sherman | Infiltration-pressurization correlation: Simplified physical modeling | |
| Contreras et al. | Observability and sensor placement problem on highway segments: A traffic dynamics-based approach | |
| CN106651036A (en) | Air quality forecasting system | |
| Wu et al. | Rethinking bus-to-metro accessibility in new town development: Case studies in Shanghai | |
| Daniel et al. | Impact of climate change on pavement performance: Preliminary lessons learned through the infrastructure and climate network (ICNet) | |
| CN105303839B (en) | The Forecasting Methodology and device in potential jam road crosspoint | |
| Zhang et al. | Prediction of urban pm 2.5 concentration based on wavelet neural network | |
| Bai et al. | A heuristic method for the minimum toll booth problem | |
| Yao et al. | UrbanVCA: A vector-based cellular automata framework to simulate the urban land-use change at the land-parcel level | |
| Dong et al. | Optimization of sensor deployment sequences for hazardous gas leakage monitoring and source term estimation | |
| Boyce et al. | Solving the sequential travel forecasting procedure with feedback | |
| Gao et al. | Distributed urban freeway traffic optimization considering congestion propagation | |
| Shen et al. | Node localization based on improved PSO and mobile nodes for environmental monitoring WSNs | |
| Freire et al. | Predicting building's corners hygrothermal behavior by using a Fuzzy inference system combined with clustering and Kalman filter | |
| CN103473476B (en) | The wind energy resources projectional technique of wind data is surveyed based on several anemometer towers in region | |
| Li et al. | Intelligent traffic data transmission and sharing based on optimal gradient adaptive optimization algorithm | |
| Shboul et al. | Spatial wind speed interpolation using Isoparametric shape functions for structural loading | |
| Guo et al. | Typhoon wind hazard model and estimation on return period of typhoon wind speed | |
| Cavalieri et al. | Application to selected transportation and electric networks in Italy | |
| CN110457760B (en) | Air pollution treatment method based on air pollution propagation mode | |
| CN107976514A (en) | A kind of remote-measuring equipment points distributing method based on the prediction of motor-vehicle tail-gas concentration distribution | |
| Lee et al. | Modified grey model for estimating traffic tunnel air quality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |